Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Medical professionals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    adaptive
    -0.33
     Adaptive
    -0.30
     adaptive
    -0.27
    å¾Ĥ
    -0.27
    imits
    -0.27
    cket
    -0.26
    ä¸Ģ度
    -0.26
    malink
    -0.26
    aptive
    -0.25
    adic
    -0.25
    POSITIVE LOGITS
     who
    0.29
     consulted
    0.27
    ç»ĵ
    0.27
    æ£īèĬ±
    0.27
    æ£ī
    0.26
    ucker
    0.25
    ant
    0.24
    ’s
    0.24
    ua
    0.24
    çµIJ
    0.24
    Act Density 0.008%

    No Known Activations